A Broad Range, Purposeful, Textual Inference
Abstract
The objective of DARPA's DEFT program is to create capabilities for deep natural language understanding and use them to aid analysts in identifying information sources that contain new developments of interest. The goal of the Cognitive Computation Group team has been to combine Natural Language Processing (NLP), Machine Learning (ML), and Knowledge Representation and Reasoning (KRR) techniques into new technologies that support the DEFT mission. Our project, a broad range purposeful textual inference system, was built on two pillars: 1) an innovative learning and inference approach emphasizing joint inference over a component-based architecture, and 2) a textual inference approach that supports relational analysis in multiple NLP tasks. The project focused on studying and developing four algorithmic components. The first was the aforementioned generic purposeful textual inference capability. The other three components were: (2) a Sentence Level Extended Semantic Role Labeling component that provides a complete and coherent predicate-argument representation of sentences covering multiple predicate types; (3) a Discourse Analysis component that addresses discourse phenomena including relations between events, temporal grounding of events and relations, and time lining of events; and (4) a Profiling component that provides a new way of representing, aggregating, and supporting the use of knowledge about concepts and entities in NLP.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 2018
- Accession Number
- AD1052861
Entities
People
- Dan Roth
Organizations
- University of Illinois Urbana–Champaign